Dynamic mobile charger scheduling with partial charging strategy for WSNs using deep-Q-networks

Banoth, Sanjai Prasada Rao; Donta, Praveen Kumar; Amgoth, Tarachand

doi:10.1007/s00521-021-06146-9

Cited by 33 publications

(17 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also not feasible for all applications. Deep reinforcement learning is an efficient classification and learning method, and the benefits of this approach are used for WSNs to recharge the nodes in [24]. This approach is used a partial charging strategy, so the network lifetime is longer for small WSNs.…”

Section: Single Charging Vehiclesmentioning

confidence: 99%

Mixed Linear Programming for Charging Vehicle Scheduling in Large-Scale Rechargeable WSNs

et al. 2022

View full text Add to dashboard Cite

Because wireless sensor networks (WSNs) have low-constrained batteries, optimizing the network lifetime is a primary challenge. Rechargeable batteries are a solution to prolong the lifetime of a sensor node instead of restricting their functionalities to save energy. Wireless energy transmitters have the added benefit of providing a charger for the batteries of the sensor nodes in the WSN. However, scheduling one or more charging vehicles efficiently to recharge multiple sensor nodes is challenging. In this context, this paper provides a solution to recharge the sensor nodes using charging vehicle scheduling in WSNs through a mixed linear programming approach. Initially, we identify a heuristic value of each sensor node based on their residual energy, distance from a charging vehicle, available data packets, and other metrics. Further, a set of nodes is recharged by identifying the best charging vehicle to prolong their lifetimes, as well as the lifetime of the network as a whole. We simulated the proposed approach using a Python simulator, tested using different performance metrics, and compared using the recently published works. We notice the superior performance of the proposed work under various metrics in time and query-driven WSNs.

show abstract

Section: Single Charging Vehiclesmentioning

confidence: 99%

Mixed Linear Programming for Charging Vehicle Scheduling in Large-Scale Rechargeable WSNs

et al. 2022

View full text Add to dashboard Cite

show abstract

“…DQN 29,30 algorithm can adapt to the complex and changeable environment, effectively reduce the possibility of training oscillation divergence, and increase the stability of the algorithm. DQN algorithm is used to optimize the routing of wireless sensor networks.…”

Section: Related Workmentioning

confidence: 99%

“…In this paper, an energy-efficient clustering algorithm combined interval type-2 fuzzy logic and dual-super-clusterhead mechanism (IT2FL-DSCH) is compared with LEACH, 23,24 LEACH-C, 25,26 DEEC, 27,28 DQN, 29,30 and TTDFP, 31,51 respectively. As can be clearly seen from Figure 25, with the increase LEACH and DEEC running times, the surviving nodes in the network are almost the same, the survival rate of LEACH-C and DQN algorithm are better than that of the two algorithms, the TTDFP algorithm is superior to LEACH, DEEC, LEACH-C, and DQN algorithms in the survival rate of sensor nodes, while the slope of IT2FL-DSCH is obviously lower than that of the other five algorithms.…”

Section: Simulation Analysismentioning

confidence: 99%

An energy‐efficient clustering algorithm combined interval type‐2 fuzzy logic and dual‐super‐cluster‐head mechanism for homogeneous wireless sensor networks of mobile sink

Xiao

Gan

Wang

et al. 2022

Int J Communication

View full text Add to dashboard Cite

Summary In recent trends, wireless sensor network (WSN) is often used in harsh environments. When WSNs work, they need to deploy a large number of sensor nodes in the monitoring area. Due to the limited resources carried by the sensor nodes, the monitoring process of WSN will be limited by the energy of the sensor nodes. An energy‐efficient clustering algorithm combining interval type‐2 fuzzy logic and dual‐super‐cluster‐head (IT2FL‐DSCH) mechanism is proposed, aiming at reducing and balancing the energy consumption of sensor nodes. Considering the four fuzzy parameters, that is, cluster heads' (CHs') battery power, CHs' centrality, base station's (BS's) mobility, and the distance from CHs to BS, interval type‐2 fuzzy logic (IT2FL) is used to select the appropriate super cluster head (SCH). And SCH is the only way to communicate with the mobile BS, thus effectively using bandwidth. Then, the DSCH mechanism to balance the energy consumption of SCH is introduced in detail. In addition, we utilize mathematical derivation to obtain the supremum of the energy consumption of the SCH algorithm under different network distribution. Finally, the MATLAB simulation results show that this protocol outperforms low energy adaptive clustering hierarchy (LEACH), LEACH‐centralized (LEACH‐C), distributed energy efficient clustering (DEEC), WSNs using deep‐Q‐networks (DQN), and two‐tier distributed fuzzy logic based protocol (TTDFP) in terms of sensor nodes energy saving, network stability, and network lifetime.

show abstract

“…To recharge the nodes with different energy consumption rates, the adaptive threshold for charging requests was considered in this study. To prolong the life of WSN and minimize the travel distance of mobile chargers, a dynamic mobile charger scheduling (DPMCS) scheme is proposed in the literature [21]. e node requests a charge before it runs out of energy and the mobile charger charges it.…”

Section: Related Workmentioning

confidence: 99%

“…e simulation results show that the stop-wait algorithm can achieve a better EUE of WSN compared with DPMCS [21], MUC [34], BNRS [35], and VN-MOAC [36] algorithms. Compared with existing cooperative mobile recharge schemes, our proposed algorithm contributes the following improvements:…”

Section: Cooperative Schemes Of the Mwrsnmentioning

confidence: 99%

Cooperative Recharge Scheme Based on a Hamiltonian Path in Mobile Wireless Rechargeable Sensor Networks

Liu

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The energy problem and limited capacity of batteries have been fundamental constraints in many wireless sensor network (WSN) applications. For WSN, the wireless energy transmission technology based on magnetic resonance coupling is a promising energy transmission technology. To reduce the cost and energy consumption during charging in mobile wireless rechargeable sensor networks (MWRSNs), a cooperative mobile charging mechanism based on the Hamiltonian path is proposed in this paper. To improve the charging task interval, we study the use of a mobile charger (MC) as a mobile sink node to collect the data in this paper. Then, we used the sink and the charging sensors selected by the MC to construct the undirected complete graph. Finally, the Euclidean distance between nodes is used as the edge weight and a Hamiltonian loop is found by using the improved Clark–Wright (C-W) saving algorithm to solve the problem of charging a rechargeable sensor network. In addition to the energy usage efficiency (EUE) and the network lifetime, the average energy loss per unit time is considered as the evaluation index according to the impact of the MC on the energy consumption during charging. The simulation results show that the proposed scheme increases the average network lifetime, decreases the average energy loss per unit time, and improves the EUE.

show abstract

Dynamic mobile charger scheduling with partial charging strategy for WSNs using deep-Q-networks

Cited by 33 publications

References 28 publications

Mixed Linear Programming for Charging Vehicle Scheduling in Large-Scale Rechargeable WSNs

Mixed Linear Programming for Charging Vehicle Scheduling in Large-Scale Rechargeable WSNs

An energy‐efficient clustering algorithm combined interval type‐2 fuzzy logic and dual‐super‐cluster‐head mechanism for homogeneous wireless sensor networks of mobile sink

Cooperative Recharge Scheme Based on a Hamiltonian Path in Mobile Wireless Rechargeable Sensor Networks

Contact Info

Product

Resources

About